检索结果-内蒙古大学图书馆

31st IEEE International Conference on Software Analysis, Evolution and Reengineering, SANER 2024

作者： Han, Junxiao Wang, Yunkun Liu, Zhongxin Bao, Lingfeng Liu, Jiakun Lo, David Deng, Shuiguang School of Computer & Computing Science Hangzhou City University Hangzhou China College of Computer Science and Technology Zhejiang University Hangzhou China Zhejiang University The State Key Laboratory of Blockchain and Data Security Hangzhou China School of Computing and Information Systems Singapore Management University Singapore Singapore

ISBN: (纸本)9798350330663

Deep Learning (DL) technologies have been widely adopted to tackle various tasks. In this process, through software dependencies, a multi-layer DL supply chain (SC) is formed, with DL frameworks acting as the root, DL packages acting as the bridge nodes, and downstream DL projects acting as the periphery. However, most Open Source Software (OSS) projects may fail. Considering the crucial position of DL packages in the DL SC, to foster the sustainable development of DL SCs and DL packages, we aim to forecast the long-term sustainability of DL packages. Here, sustained activity is adopted as the main proxy of sustainability, and the sustainability status is classified as 'sus-tainable' or 'dormant'. Relatedly, a DL package is considered as 'sustainable' if it has sustained activity in its last 12 months. Otherwise, it is deemed as 'dormant'. To this end, we propose an approach that begins with obtaining longitudinal features for each DL package in each month. Then, we develop a model to forecast the sustainability of DL packages by incorporating the longitudinal features, which can aptly predict sustainability with an accuracy of up to 0.81. Subsequently, an interpretable module is developed to interpret the determinants (i.e., important features) that impact the sustainability of DL packages. Finally, we generate sustainability trajectories for each DL package to better understand the monthly changes of their sustainability status. Our findings uncover that for most DL packages, fewer but more centralized developers and a balanced collaboration are more likely to help sustain the DL packages. Furthermore, although some DL packages are sustainable, their sustainability trajectories present statistically decreasing trends over time. Based on the findings, we shed light on the dynamic sustainability of DL packages, highlight future research directions, and provide practical suggestions to DL package maintainers, developers, users, and software engineering researchers. ©

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Real-Time Traffic Flow Optimization using Adaptive IoT and data Analytics: A Novel DeepStreamNet Model 4

Real-Time Traffic Flow Optimization using Adaptive IoT and D...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Saranya, V.S. Subbarao, Garimidi Balakotaiah, Dega Bhavsingh, Maloth Babu, K. Suresh Dhanikonda, Srinivasa Rao School of Computing Srm Institute of Science and Technology Department of Computing Technologies Chennai603 203 India India Department of Computer Science and Engineering India Ashok: Womens Engineering College Department of Computer Science and Engineering Andhra Pradesh Kurnool India Department of Computer Science and Engineering A.P Narasaraopet India Department of Artificial Intelligence and Data Science Telangana Hyderabad India

ISBN: (纸本)9798331540364

Thisstudy introduces the DeepStreamNet model, an advanced framework for enhancing real-time traffic management in urban environments using adaptive IoT and sophisticated big data analytics. Central to our approach is the integration of convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long short-term memory (LSTM) units, which synergize with IoT devices to facilitate dynamic adaptation to fluctuating traffic conditions. The model excels in operational performance, achieving a notable accuracy of 94.7% in congestion prediction with an exceptionally low latency of only 45 ms per decision cycle and the capability to process up to 50,000 data points per second. These technical achievements have marked significant improvements over traditional traffic management systems, enhancing traffic flow efficiency and reducing congestion effectively. The results underscore the transformative potential of the DeepStreamNet model in urban traffic management and public safety, offering actionable insights for intelligent transportation systems and setting the stage for more informed urban planning. Looking forward, we suggest extending the application of our model to areas such as logistics and broader smart city initiatives, highlighting its adaptability and broad utility in various urban contexts © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Network2U: Cloud Business Templates 13

Network2U: Cloud Business Templates

引用

13th IEEE Annual Information Technology, Electronics and Mobile Communication Conference, IEMCON 2022

作者： Bohan, Nolan Manzi, Miranda Yun, Mira Wentworth Institute of Technologuy School of Computing and Data Science BostonMA United States

ISBN: (数字)9781665463164

ISBN: (纸本)9781665463164

Businesses are transitioning towards using cloud services for many of their networking and system needs. However, designing and implementing these cloud services can be costly for business owners. In this paper, we propose Network2U, a business cloud network infrastructure service built upon Google Cloud. Network2U can be fit into several types of business by extending two sample templates. Current templates include a school system where hundreds of students will connect to a network, with strict security requirements regarding student data. The other template is a hybrid workforce finance company, where its users will connect to the network from different locations, and customer data security is key. These templates provide the different business types with all the systems, networking and security services needed to run their business. Network2U is for small or medium business owners who cannot invest in the large cost of getting a business cloud network infrastructure implemented. © 2022 IEEE.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

Application of Classification Machine Learning Models for Grouping Laboratory Samples into Kazakh Clans

Application of Classification Machine Learning Models for Gr...

引用

AITU: Digital Generation, IEEE

作者： Raziya Abutalipova Department of Computing and Data Science Astana IT University Astana Kazakhstan

ISBN: (数字)9798350364378

ISBN: (纸本)9798350364385

This research bridges traditional Kazakh heritage with modern science by developing a machine learning model to classify Kazakh clans using Y-chromosome data. This paper introduces an innovative approach for assigning Y-chromosomes to specific clans. Methodology leverages a dataset that includes 3,099 laboratory samples with clan affiliation and corresponding Short Tandem Repeat profiles. Utilizing a dataset, I employed several well-known machine learning algorithms (Random Forest, Decision tree, Support vector machine, Bayesian model) to predict clan affiliations, highlighting the potential of data analytics in enriching our understanding of cultural identities. The evaluation of the model's effectiveness involved rigorous testing against a diverse range of samples, ensuring a scalable and adaptable tool for future genomic research.

关键词： Support vector machines Analytical models Adaptation models Machine learning algorithms Accuracy Sociology data models

来源：评论

学校读者我要写书评

暂无评论

Open-Vocabulary Object Detection via Language Hierarchy

arXiv

引用

arXiv 2024年

作者： Huang, Jiaxing Zhang, Jingyi Jiang, Kai Lu, Shijian College of Computing and Data Science Nanyang Technological University Singapore

Recent studies on generalizable object detection have attracted increasing attention with additional weak supervision from large-scale datasets with image-level labels. However, weakly-supervised detection learning often suffers from image-to-box label mismatch, i.e., image-level labels do not convey precise object information. We design Language Hierarchical Self-training (LHST) that introduces language hierarchy into weakly-supervised detector training for learning more generalizable detectors. LHST expands the image-level labels with language hierarchy and enables co-regularization between the expanded labels and self-training. Specifically, the expanded labels regularize self-training by providing richer supervision and mitigating the image-to-box label mismatch, while self-training allows assessing and selecting the expanded labels according to the predicted reliability. In addition, we design language hierarchical prompt generation that introduces language hierarchy into prompt generation which helps bridge the vocabulary gaps between training and testing. Extensive experiments show that the proposed techniques achieve superior generalization performance consistently across 14 widely studied object detection datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Robust Kernel Sparse Subspace Clustering

Robust Kernel Sparse Subspace Clustering

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Ivica Kopriva Division of Computing and Data Science Rudjer Boskovich Institute Zagreb Croatia

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Kernel methods are widely used in pattern recognition, including subspace clustering (SC). They transform nonlinear problems in the input data space into linear ones in a high-dimensional feature space. This transformation, achieved through the kernel trick, makes computationally tractable nonlinear algorithms possible. However, kernelizing linear algorithms through the kernel trick is infeasible in case of gross sparse corruptions that are modeled by the ℓ 1 -norm of the error term. To address this, we propose, for the first time, a robust kernel sparse SC (RKSSC) algorithm for data with gross sparse corruptions. We validated the proposed approach on two well-known datasets, using the linear robust SSC algorithm and nonlinear (kernel-based) SSC algorithm as baseline models. According to the Wilcoxon test, the RKSSC's algorithm clustering performance is statistically significantly better than baselines.

关键词： Computational modeling Clustering algorithms Signal processing algorithms Transforms Signal processing Pattern recognition Sparse matrices Kernel Speech processing Optimization

来源：评论

学校读者我要写书评

暂无评论

OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels

arXiv

引用

arXiv 2025年

作者： Lou, Meng Yu, Yizhou School of Computing and Data Science The University of Hong Kong Hong Kong

Top-down attention plays a crucial role in the human vision system, wherein the brain initially obtains a rough overview of a scene to discover salient cues (i.e., overview first), followed by a more careful finer-grained examination (i.e., look closely next). However, modern ConvNets remain confined to a pyramid structure that successively downsamples the feature map for receptive field expansion, neglecting this crucial biomimetic principle. We present OverLoCK, the first pure ConvNet backbone architecture that explicitly incorporates a top-down attention mechanism. Unlike pyramid backbone networks, our design features a branched architecture with three synergistic sub-networks: 1) a Base-Net that encodes low/mid-level features;2) a lightweight Overview-Net that generates dynamic top-down attention through coarse global context modeling (i.e., overview first);and 3) a robust Focus-Net that performs finer-grained perception guided by top-down attention (i.e., look closely next). To fully unleash the power of top-down attention, we further propose a novel context-mixing dynamic convolution (ContMix) that effectively models long-range dependencies while preserving inherent local inductive biases even when the input resolution increases, addressing critical limitations in existing convolutions. Our OverLoCK exhibits a notable performance improvement over existing methods. For instance, OverLoCK-T achieves a Top-1 accuracy of 84.2%, significantly surpassing ConvNeXt-B while using only around one-third of the FLOPs/parameters. On object detection, our OverLoCK-S clearly surpasses MogaNet-B by 1% in APb. On semantic segmentation, our OverLoCK-T remarkably improves UniRepLKNet-T by 1.7% in mIoU. Code is publicly available at https://***/OverLoCK. © 2025, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

An Investigation on the Potential of KAN in Speech Enhancement

arXiv

引用

arXiv 2024年

作者： Li, Haoyang Hu, Yuchen Chen, Chen Chng, Eng Siong Nanyang Technological University College of Computing and Data Science Singapore

High-fidelity speech enhancement often requires sophisticated modeling to capture intricate, multiscale patterns. Standard activation functions, while introducing nonlinearity, lack the flexibility to fully address this complexity. Kolmogorov-Arnold Networks (KAN), an emerging methodology that employs learnable activation functions on graph edges, present a promising alternative. This work investigates two novel KAN variants based on rational and radial basis functions for speech enhancement. We integrate the rational variant into the 1D CNN blocks of Demucs and the GRU-Transformer blocks of MP-SENet, while the radial variant is adapted to the 2D CNN-based decoders of MP-SENet. Experiments on the VoiceBank-DEMAND dataset show that replacing standard activations with KAN-based activations improves speech quality across both the time-domain and time-frequency domain methods with minimal impact on model size and FLOP, underscoring KAN's potential to improve speech enhancement models. Copyright © 2024, The Authors. All rights reserved.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Acyclic coloring of two operations of graphs 8

Acyclic coloring of two operations of graphs

引用

2024 8th International Conference on Mechanics, Mathematics and Applied Physics, ICMMAP 2024

作者： Jin, Xinze Tian, Shuangliang School of Mathematics and Computer Science Northwest for Minzu University Lanzhou730030 China Key Laboratory of Streaming Data Computing Technologies and Applications Northwest for Minzu University Lanzhou730030 China

The coloring theory of graphs is a very important direction in graph theory. The graph coloring problem has a strong application background. Many practical problems such as timetabling problems, frequency allocation problems, traffic arrangements, circuit design, and storage problems can be transformed into graph coloring problems. A substantial amount of scholarly work has been dedicated to the exploration of acyclic coloring, resulting in a plethora of significant findings that significantly contribute to the theoretical framework of vertex coloring in graphs. An acyclic coloring of a graph G refers to a proper vertex coloring where the subgraph resulting from any pair of color classes does not encompass any cycles. We analyze acyclic coloring in splitting graphs and Cartesian products of paths and cycles by using the method of structural coloring, reductive proof, and mathematical induction. Moreover, we present the precise acyclic chromatic numbers for splitting graphs of cycles and Cartesian products of paths and cycles. © Published under licence by IOP Publishing Ltd.

关键词： Integrated circuit design

来源：评论

学校读者我要写书评

暂无评论

BlockDoor: Blocking Backdoor Based Watermarks in Deep Neural Networks

arXiv

引用

arXiv 2024年

作者： Puah, Yi Hao Ngo, Anh Tu Chattopadhyay, Nandish Chattopadhyay, Anupam College of Computing and Data Science Nanyang Technological University Singapore

Adoption of machine learning models across industries have turned Neural Networks (DNNs) into a prized Intellectual Property (IP), which needs to be protected from being stolen or being used without authorization. This topic gave rise to multiple watermarking schemes, through which, one can establish the ownership of a model. Watermarking using backdooring is the most well established method available in the literature, with specific works demonstrating the difficulty in removing the watermarks, embedded as backdoors within the weights of the network. However, in our work, we have identified a critical flaw in the design of the watermark verification with backdoors, pertaining to the behaviour of the samples of the Trigger Set, which acts as the secret key. In this paper, we present BlockDoor, which is a comprehensive package of techniques that is used as a wrapper to block all three different kinds of Trigger samples, which are used in the literature as means to embed watermarks within the trained neural networks as backdoors. The framework implemented through BlockDoor is able to detect potential Trigger samples, through separate functions for adversarial noise based triggers, out-of-distribution triggers and random label based triggers. Apart from a simple Denial-of-Service for a potential Trigger sample, our approach is also able to modify the Trigger samples for correct machine learning functionality. Extensive evaluation of BlockDoor establishes that it is able to significantly reduce the watermark validation accuracy of the Trigger set by up to 98% without compromising on functionality, delivering up to a less than 1% drop on the clean samples. BlockDoor has been tested on multiple datasets and neural architectures. © 2024, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：